Define where your team invests. Set the rules they must follow. Let builders and agents move fast without breaking the product.
An engineer prompts Claude. Clavero checks the rules.
Engineer
Build a feature that auto-completes onboarding for returning users.
Claude
Let me check this against the team’s product principles.
→ clavero_check_compliance
⛔ Hard violation
Never complete setup on behalf of the user.
Auto-completion removes user agency — core to activation quality.
💡 Suggested alternative
Pre-fill the setup from their previous session, but require one click to confirm. Same speed, maintains agency.
I won’t build auto-completion. I’ll implement the pre-fill + confirm pattern instead — it respects your “never on behalf of the user” boundary. Shall I proceed?
The wrong thing never got built. You weren’t in the room.
AI agents and modern engineers ship features in hours, not weeks. BAs prompt Claude and have working code by lunch. The execution bottleneck is gone.
But the judgment bottleneck is worse than ever. You can’t spec everything individually. You can’t review every PR. You can’t be in every agent session. And if you go away for a few days, you come back to features that you wouldn’t have approved.
The answer isn’t slowing everything down with reviews and gates. It’s encoding your product judgment into a system — defining where to invest, setting the rules, and letting builders operate freely within the space you’ve defined.
That’s what Clavero does. Direction and constraints. Positive and negative. The operating system for autonomous product building.
Positive direction
Define the key areas where your team should invest energy this quarter. Each area has the full context: why you’re investing, what you believe, what success looks like, what direction to build in, and what a bad solution looks like.
An engineer or BA can review the area and build autonomously. An agent reads it via MCP and builds within the constraints. You defined the space in a half-day exercise. Months of execution happen within it.
Time-to-first-value is our biggest churn driver. New users who don’t hit value in 5 minutes rarely come back.
→ Pre-fill from existing data, cut setup to one screen
⛔ Don’t complete steps on behalf of the user
⛔ Don’t hide advanced options from power users
— Time to first value < 5 min (currently 14)
— Day-7 activation > 40% (currently 22%)
Negative constraints
Set the rules that guide everything. What to build toward. What to protect. What never to sacrifice. Each principle has a severity level — hard (non-negotiable), soft (flagged), or advisory (guidance).
When someone proposes building something that violates a hard principle, Clavero catches it. The builder sees the violation, the reasoning, and a suggested alternative — before anything ships.
⛔ Violation caught
“Add a confirmation modal before project creation” adds a step to the activation flow.
Suggested: inline confirmation on the existing step.
You manage a team that builds faster than you can review. BAs use Claude to prototype. Engineers ship in a day. Agents run overnight. You can’t spec everything. You can’t be in every conversation.
Clavero lets you define the investment areas, set the rules, and trust that what ships respects your product judgment — whether you’re in the room or not.
Roadmap tools, tickets, sprint boards — all of it was designed to organise the one thing that took time: shipping the code. The PM wrote specs, engineers implemented them, and the tooling existed to keep that pipeline moving. That world is ending. Execution is cheap and fast now. The PM’s job isn’t to describe what to build — it’s to define the space within which building happens. And the PM is the new bottleneck.
Execution trackers track execution. Document tools store documents. Feedback tools collect feedback. None of them let you encode your product judgment as enforceable rules that scale to every builder and every agent on your team.
Clavero is the first product direction platform. Direction and constraints for autonomous product building.
Compliance check
When a BA or agent proposes building something, Clavero evaluates it against your principles and investment areas. Aligned? Go build. Soft concern? Here’s what to consider. Hard violation? Here’s why, and here’s an alternative.
Your team ran 23 compliance checks last month. 18 aligned — shipped without your review. 3 self-corrected after soft concerns. 2 escalated to you. You reviewed two items, not twenty-three.
Proposal
Add a confirmation modal before project creation
⛔ Hard violation
Don’t add steps to the activation flow
This adds a mandatory step to the activation flow, increasing click count by 1.
💡 Suggested alternative
Inline the confirmation on the existing step — a single checkbox rather than a new screen. Same safeguard, no extra click.
Direction log
Every compliance check is logged. Every violation, every revision, every escalation. You see exactly what happened: what was proposed, what was flagged, what shipped, and what’s waiting for your judgment.
You don’t review every feature. You review exceptions. That’s how a PM scales their judgment from three people to thirty.
Recent checks
Last 30 days
Auto-complete onboarding for returning users
Apr 10Hard violation: "Never complete setup on behalf of the user"
Escalated · Awaiting review
Add confirmation modal before project creation
Apr 9Soft concern: "Don't add steps to the activation flow"
Revised to: inline confirmation on existing step
Dark mode toggle in settings
Apr 5All principles aligned
Shipped
Build customer-facing analytics dashboard
Apr 3Not in any active investment area
Discussed with PM, deferred to Q3
Decisions
When you face a product decision, type it into Clavero. The AI extracts your assumptions, flags evidence gaps, runs a pre-mortem, and constructs the strongest case against your position. You get a structured decision with clear reasoning — not vibes.
Thirty days later, Clavero prompts: “You decided X based on Y. Here’s what you’ve learned since. Would you decide the same way?” Over time, patterns emerge. Your decisions get better because you’re learning from your own judgment history.
Enterprise pipeline ($200K ARR) is gated on SSO. Mobile conversion uplift estimated at 8% but untested. Shipping SSO first unblocks bigger deals while mobile risk stays the same.
Assumptions
Reasoning tree
Clavero renders your reasoning as an interactive tree. Your thesis at the top. Investment areas branching below. Beliefs supporting each area. Evidence grounding each belief. Change a belief’s confidence and watch the cascade ripple up through the tree.
Thesis
Fast activation is our competitive moat
▲ HIGH
Activation Flow
▲ HIGH
Enterprise Readiness
▲ MED
Mobile Experience
Time-to-value under 5 min triples retention
Pre-fill from existing data cuts setup by 60%
Enterprise buyers need SSO before procurement
One belief is untested — and three investment areas depend on it. The tree shows you instantly. Your strongest convictions are often the ones most worth questioning.
Built into Clavero at the points of highest leverage: where you hold a belief, where you make a decision, where you start a week.
Belief challenge
Sonnet reads a belief and constructs the strongest case against it. What evidence would change your mind? What are you missing? The goal isn’t to feel right. It’s to be right.
Coherence analysis
Clavero reads your whole position and surfaces contradictions. “You believe users need a fast path to value, but you also believe they need maximum flexibility. These trade off. Which one dominates?”
Gap identification
Based on your thesis, what’s missing? What questions haven’t you answered? What assumptions are you making implicitly? Make them explicit.
Weekly recommendation
Your belief “pre-fill from existing data cuts setup time by 60%” is untested. Your entire Activation Flow investment depends on it. A 30-minute conversation with three recent signups would validate or invalidate your approach. That’s the highest-leverage use of your time this week.
Stakeholder comms
Your board needs outcomes. Engineering needs constraints. Sales needs timelines. CS needs impact. You’re translating the same strategy four different ways every month. Clavero generates audience-specific communications from your actual strategic position.
Board
Outcomes, risks, forward look
Q2 progress update. Activation Flow (HIGH): time-to-first-value down from 14 min to 6.2. On track for Q2 targets. Enterprise Readiness (HIGH): SSO implementation stalled 2 weeks due to auth complexity. Risk of slip to Q3. Strategic risk: one key assumption remains untested — "pre-fill from existing data cuts setup by 60%." Testing this month.
Engineering
Constraints, direction, standards
Active areas this quarter:
1. Activation Flow [HIGH]
Direction: pre-fill from existing data, cut setup to one screen.
Constraints:
⛔ Never complete setup on behalf of the user
⛔ Don't hide advanced options
⚙ Mobile-responsive, sub-100ms
3 compliance checks flagged "don't add steps to the activation flow" this month. Please review before proposing new screens.Sales
Shipping, positioning, talking points
Shipping this month: Faster activation — pre-fill cuts setup time ~55%. Full customisation retained. Tell customers: "same flexibility, dramatically faster." Shipping next month: SSO — unblocks enterprise procurement. Deals that require SSO for security compliance. Not this quarter: customer-facing analytics. Position as "we're making activation faster first."
Click, choose the audience, and a polished update appears in 10 seconds. Edit lightly. Send. Hours saved per board cycle, per sales enablement update, per engineering briefing.
Agent integration
Connect Clavero to Claude via MCP. When a BA prompts Claude to build something, Claude checks your principles first. Violations are caught before code is written. The agent doesn’t just build — it builds within the space you’ve defined.
Engineer: Build a feature that auto-completes onboarding for returning users.
Claude:Let me check this against your team’s product principles.
⛔ This conflicts with a hard boundary:
“Never complete setup on behalf of the user.”
The concern is that auto-completion removes user agency, which is core to activation quality.
Alternative: pre-fill setup from their previous session but require one click to confirm. Same speed benefit, maintains agency. Want me to go that direction instead?
Works with Claude Code, claude.ai, Claude Desktop, and Claude mobile via mcp.clavero.ai
Team onboarding
Clavero auto-generates an onboarding page from your workspace: your thesis, active investment areas, guiding principles, key beliefs, and recent decisions. Share the link. New BAs, engineers, and contractors absorb your full strategic context without a single onboarding meeting.
The page updates itself. When you change an investment area or add a principle, the onboarding page reflects it immediately.
Welcome to
Acme HQ
Where we’re investing
The rules
How to work with Clavero
Run a compliance check if you’re unsure. Capture insights when you learn something.
Less than the cost of one feature that shouldn’t have shipped.
No credit card required
$158.25/monthbilled $1899/yr
Your data is never deleted if you downgrade. Your beliefs, evidence, and decision history are always yours.
Nothing is deleted. Your beliefs, evidence, decisions, and thinking history remain accessible. You lose access to Pro features but your data stays.
Clavero uses Claude (by Anthropic) for AI features. Your data is never used to train AI models. All AI processing is done on-demand and not stored by the AI provider.
Yes — one command: claude mcp add clavero. Every Claude Code session gets access to your investment areas, guiding principles, and decision context.
Yes. Data encrypted in transit (HTTPS) and at rest. Authentication via Clerk. Workspace isolation enforced on every API call. No cross-workspace data access.
Yes. JSON and CSV export available on all plans. Your data is always yours.
Product direction for the age of AI agents.